Volumetric Data Post-Production and Distribution System

1. A method, comprising: receiving, by a device comprising a processor, a group of images; determining, by the device, first points of interest of a first image of the group of images and second points of interest of a second image of the group of images; comparing, by the device, the first points of interest to the second points of interest; and determining, by the device using a non-linear least squares minimization with loss function, from the first points of interest and the second points of interest and based on a result of the comparing, sets of candidate coordinate positions of a joint of a character represented in the first image and the second image.

2. The method of claim 1 , wherein the first image is captured from a first vantage point applicable to a scene in which the character is represented, and the second image is captured from a second vantage point applicable to the scene.

3. The method of claim 2 , wherein respective images of the group of images comprise respective location data corresponding to respective locations of capture of the respective images, and wherein a first location of capture of the first image defines the first vantage point and a second location of capture of the second image defines the second vantage point.

4. The method of claim 1 , wherein the determining the sets of candidate coordinate positions of the joint comprises determining respective confidence levels for respective sets of the sets of candidate coordinate positions of the joint.

5. The method of claim 4 , further comprising: selecting, by the device, a final coordinate position of the joint, wherein the final coordinate position comprises a set of the sets of candidate coordinate positions having at least a threshold confidence level among the respective confidence levels of the sets of candidate coordinate positions.

6. The method of claim 5 , wherein the joint is a first joint, and further comprising: generating, by the device, a bone comprising the final coordinate position of the first joint and a coordinate position of a second joint, wherein the bone corresponds to a skeletal structure of the character.

7. The method of claim 6 , further comprising: generating, by the device, for an image of the group of images, a first set of linear blended bone weights for vertices of the skeletal structure and a second set of linear blended bone weights for vertices of the skeletal structure, wherein the vertices comprise information representative of the first joint and the second joint.

8. The method of claim 7 , further comprising: reducing, by the device, the first set of linear blended bone weights for the vertices of the skeletal structure and the second set of linear blended bone weights for the vertices of the skeletal structure, the reducing comprising blending the first set of linear blended bone weights and the second set of linear blended bone weights to a final set of linear blended bone weights for the vertices of the skeletal structure.

9. The method of claim 8 , further comprising: skinning, by the device, a mesh of the character of the image of the group of images corresponding to the final set of linear blended bone weights.

10. A system, comprising: a processor; and a memory that stores executable instructions that, when executed by the processor, facilitate performance of operations, comprising: retrieving a group of images of a humanoid character; determining points of interest of the humanoid character for each image of the group of images; locating, using a non-linear least squares minimization with loss function, each joint of a group of joints of the humanoid character corresponding to the points of interest; and creating a skeletal structure of the humanoid character comprising the group of joints.

11. The system of claim 10 , wherein each point of the points of interest comprises three dimensions.

12. The system of claim 10 , wherein the group of joints comprises at least two of a root, a left hip, a right hip, or a lower neck.

13. The system of claim 12 , wherein the operations further comprise: associating, for the images of the group of images, respective location of respective joints of the group of joints with respective times of capture of the images.

14. The system of claim 13 , wherein the operations further comprise: determining an orientation of the skeletal structure using the at least two of the root, the left hip, the right hip, or the lower neck.

15. The system of claim 13 , wherein the operations further comprise: determining at least one rotation for the respective joints from the respective locations, the respective times of capture, and the orientation of the skeletal structure.

16. A machine-readable storage medium, comprising executable instructions that, when executed by a processor of a system, facilitate performance of operations, comprising: accessing a volumetric recording of an object; and in response to the accessing, determining points of interest of the object in the volumetric recording, wherein the points of interest comprise surface features of the object, and generating, using a non-linear least squares minimization with loss function, a three dimensional skeletonization corresponding to the points of interest of the object.

17. The machine-readable storage medium of claim 16 , wherein the object is a first object, wherein the surface features are determined to be characteristics of the first object, and wherein the points of interest of the first object are determined by mapping the points of interest of the first object to a second object, stored in in association with the system, that satisfy a similarity criterion for being similar to the first object.

18. The machine-readable storage medium of claim 16 , wherein the operations further comprise: exporting the three dimensional skeletonization to one of a cloud server or a local storage.

19. The machine-readable storage medium of claim 16 , wherein the volumetric recording comprises a group of recordings from different camera positions.

20. The machine-readable storage medium of claim 19 , wherein the points of interest comprise homologous three dimensional coordinates from the group of recordings.